Stereoscopic motion is an approach for comparing image change due to motion in a stereo pair of image sequences. Qualitatively, the relative image change shows that an object point is approaching, receding, or remaining at constant depth. Quantitatively, the relative change predicts where the object point will pass with respect to the camera system.

In dynamic scenes, the presence of object boundaries is often signaled by the appearance or disappearance of occluded surfaces over time. Such regions of surface accretion or deletion can be found using matching techniques similar to those used to determine optical flow in an image sequence. Regions in one frame that are not adequately matched by any region in previous frames correspond to accretion. Regions that have no matches in subsequent frames correspond to deletion. In either case, an occlusion boundary is present. Furthermore, by associating accretion or deletion regions with a surface on one side of a boundary, it is possible to determine which side of the boundary is being occluded. This association can be based purely on visual motion-the accretion or deletion region moves with the same image velocity as the remaining visible surface to which it is attached.

Optical flow can be used to locate dynamic occlusion boundaries in an image sequence. We derive an edge detection algorithm sensitive to changes in flow fields likely to be associated with occlusion. The algorithm is patterned after the Marr-Hildreth zero-crossing detectors currently used to locate boundaries in scalar fields. Zero-crossing detectors are extended to identify changes in direction and/or magnitude in a vector-valued flow field. As a result, the detector works for flow boundaries generated due to the relative motion of two overlapping surfaces, as well as the simpler case of motion parallax due to a sensor moving through an otherwise stationary environment. We then show how the approach can be extended to identify which side of a dynamic occlusion boundary corresponds to the occluding surface. The fundamental principal involved is that at an occlusion boundary, the image of the surface boundary moves with the image of the occluding surface. Such information is important in interpreting dynamic scenes. Results are demonstrated on optical flow fields automatically computed from real image sequences.